Download
OpenOCR is an open-source General OCR toolkit developed by the OCR team at Fudan University for research and real-world document processing applications. It provides a unified platform for text detection, text recognition, formula recognition, table recognition, and document parsing. Built on advanced OCR technologies such as SVTRv2 and UniRec-0.1B, OpenOCR delivers high accuracy while maintaining efficient inference performance. The toolkit supports both Chinese and English content, making it suitable for multilingual document analysis. OpenOCR includes training, evaluation, fine-tuning, and deployment tools, allowing users to customize models for specific OCR tasks. Its comprehensive ecosystem bridges academic research and industrial applications through reproducible benchmarks and commercial-grade OCR solutions.
Features
- Supports text detection and recognition for both Chinese and English documents.
- Provides document parsing capabilities for extracting text, formulas, tables, and layout structures.
- Includes UniRec-0.1B for unified recognition of text, mathematical formulas, and mixed content.
- Offers fine-tuning support for custom OCR datasets and specialized use cases.
- Enables ONNX model export for wider deployment compatibility across platforms.
- Integrates a unified training and evaluation benchmark with reproductions of leading OCR research models.
